| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4B701EE2.1000006@simula.no>
Date: Mon, 08 Feb 2010 15:25:38 +0100
From: Andreas Petlund <apetlund@...ula.no>
To: "netdev@...r.kernel.org" <netdev@...r.kernel.org>
CC: Ilpo Järvinen <ilpo.jarvinen@...sinki.fi>,
Eric Dumazet <eric.dumazet@...il.com>,
Arnd Hannemann <hannemann@...s.rwth-aachen.de>,
LKML <linux-kernel@...r.kernel.org>, shemminger@...tta.com,
David Miller <davem@...emloft.net>,
william.allen.simpson@...il.com
Subject: [net-next PATCH v2 2/3] net: TCP thin linear timeouts
Major change: Limit number of thin linear timeout tries to TCP_THIN_LT_RETRIES (currently 6).
>From ec71404702149bc9197c749e5d1d68656c87f98f Mon Sep 17 00:00:00 2001
From: Andreas Petlund <apetlund@...ula.no>
Date: Mon, 8 Feb 2010 14:05:53 +0100
Subject: [PATCH 2/3] net: TCP thin linear timeouts
Signed-off-by: Andreas Petlund <apetlund@...ula.no>
---
include/linux/sysctl.h | 1 +
include/linux/tcp.h | 3 +++
include/net/tcp.h | 4 ++++
net/ipv4/sysctl_net_ipv4.c | 7 +++++++
net/ipv4/tcp.c | 5 +++++
net/ipv4/tcp_timer.c | 19 ++++++++++++++++++-
6 files changed, 38 insertions(+), 1 deletions(-)
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 9f236cd..d840d75 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -425,6 +425,7 @@ enum
NET_TCP_ALLOWED_CONG_CONTROL=123,
NET_TCP_MAX_SSTHRESH=124,
NET_TCP_FRTO_RESPONSE=125,
+ NET_TCP_FORCE_THIN_LINEAR_TIMEOUTS=126,
};
enum {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 7fee8a4..67da706 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -103,6 +103,7 @@ enum {
#define TCP_CONGESTION 13 /* Congestion control algorithm */
#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
#define TCP_COOKIE_TRANSACTIONS 15 /* TCP Cookie Transactions */
+#define TCP_THIN_LT 16 /* Use linear timeouts for thin streams*/
/* for TCP_INFO socket option */
#define TCPI_OPT_TIMESTAMPS 1
@@ -341,6 +342,8 @@ struct tcp_sock {
u16 advmss; /* Advertised MSS */
u8 frto_counter; /* Number of new acks after RTO */
u8 nonagle; /* Disable Nagle algorithm? */
+ u8 thin_lt : 1,/* Use linear timeouts for thin streams */
+ thin_undef : 7;
/* RTT measurement */
u32 srtt; /* smoothed round trip time << 3 */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e5e2056..bc5856a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -196,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCP_NAGLE_CORK 2 /* Socket is corked */
#define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */
+/* TCP thin-stream limits */
+#define TCP_THIN_LT_RETRIES 6 /* After 6 linear retries, do exp. backoff */
+
extern struct inet_timewait_death_row tcp_death_row;
/* sysctl variables for tcp */
@@ -241,6 +244,7 @@ extern int sysctl_tcp_workaround_signed_windows;
extern int sysctl_tcp_slow_start_after_idle;
extern int sysctl_tcp_max_ssthresh;
extern int sysctl_tcp_cookie_size;
+extern int sysctl_tcp_force_thin_linear_timeouts;
extern atomic_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 7e3712c..cb2ed35 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -576,6 +576,13 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
+ .procname = "tcp_force_thin_linear_timeouts",
+ .data = &sysctl_tcp_force_thin_linear_timeouts,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d5d69ea..cbc1ee3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2229,6 +2229,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
}
break;
+ case TCP_THIN_LT:
+ if (val)
+ tp->thin_lt = 1;
+ break;
+
case TCP_CORK:
/* When set indicates to always queue non-full frames.
* Later the user clears this option and we transmit
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index de7d1bf..f01a585 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -29,6 +29,7 @@ int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL;
int sysctl_tcp_retries1 __read_mostly = TCP_RETR1;
int sysctl_tcp_retries2 __read_mostly = TCP_RETR2;
int sysctl_tcp_orphan_retries __read_mostly;
+int sysctl_tcp_force_thin_linear_timeouts __read_mostly;
static void tcp_write_timer(unsigned long);
static void tcp_delack_timer(unsigned long);
@@ -415,7 +416,23 @@ void tcp_retransmit_timer(struct sock *sk)
icsk->icsk_retransmits++;
out_reset_timer:
- icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
+ /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is
+ * used to reset timer, set to 0. Recalculate 'icsk_rto' as this
+ * might be increased if the stream oscillates between thin and thick,
+ * thus the old value might already be too high compared to the value
+ * set by 'tcp_set_rto' in tcp_input.c which resets the rto without
+ * backoff. Limit to TCP_THIN_LT_RETRIES before initiating exponential
+ * backoff behaviour to avoid continue hammering linear-timeout
+ * retransmissions into a black hole*/
+ if ((tp->thin_lt || sysctl_tcp_force_thin_linear_timeouts) &&
+ tcp_stream_is_thin(sk) && sk->sk_state == TCP_ESTABLISHED &&
+ icsk->icsk_retransmits <= TCP_THIN_LT_RETRIES) {
+ icsk->icsk_backoff = 0;
+ icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
+ } else {
+ /* Use normal (exponential) backoff */
+ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
+ }
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1))
__sk_dst_reset(sk);
--
1.6.3.3
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists